© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33290
    Prev
    Next
    INDEX
    Explanations

    multiple, both, or several

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯Ķäºļ
    -0.08
    Perfect
    -0.07
     Perfect
    -0.07
    çĽ¸ä¿¡æĪij
    -0.07
    ilen
    -0.07
    /LICENSE
    -0.07
    oare
    -0.07
    ordin
    -0.07
     عÙı
    -0.07
    erot
    -0.07
    POSITIVE LOGITS
    tober
    0.07
    åħ±è¯Ĩ
    0.07
    å¼Ĥ
    0.07
    .setdefault
    0.07
    ment
    0.06
    æīį对
    0.06
    ä½Ĩåľ¨
    0.06
     Liebl
    0.06
    åĿª
    0.06
     Grimm
    0.06
    Activations Density 0.005%

    No Known Activations